© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9670
    Prev
    Next
    INDEX
    Explanations

    elements related to legal arguments and judicial reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彼は
    -0.91
     esso
    -0.90
     himself
    -0.78
     his
    -0.76
    的他
    -0.73
    彼が
    -0.73
     he
    -0.73
    彼の
    -0.71
    his
    -0.70
     ihn
    -0.68
    POSITIVE LOGITS
     she
    2.48
     herself
    2.45
     her
    2.41
     그녀
    2.20
    herself
    2.00
     její
    1.99
    彼女の
    1.98
     hennes
    1.98
    彼女は
    1.96
    她的
    1.91
    Activations Density 2.038%

    No Known Activations